How AI frameworks control model thinking

Dev.to AI
Generative AI

Every reasoning model can think harder if you ask it to. Claude has budget_tokens and effort. OpenAI has reasoning_effort. Google has thinking levels. The API surface exists. The question is: who decides when to use it? We surveyed seven agent frameworks - Claude Code, Cursor, OpenClaw, GitHub Copilot, Windsurf, Aider, and Devin - to understand how they handle model thinking.